{ "data_id": "44498", "name": "credit-g_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "credit-g_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "a3d2d649-8cc3-4130-8fe7-c2bb5ec403c1", "description": "Subsampling of the dataset credit-g (31) with\n\nseed=0\nargs.nrows=2000\nargs.ncols=100\nargs.nclasses=10\nargs.no_stratify=True\nGenerated with the following source code:\n\n\n```python\n def subsample(\n self,\n seed: int,\n nrows_max: int = 2_000,\n ncols_max: int = 100,\n nclasses_max: int = 10,\n stratified: bool = True,\n ) -> Dataset:\n rng = np.random.default_rng(seed)\n\n x = self.x\n y = self.y\n\n # Uniformly sample\n classes = y.unique()\n if len(classes) > nclasses_max:\n vcs = y.value_counts()\n selected_classes = rng.choice(\n classes,\n size=nclasses_max,\n replace=False,\n p=vcs \/ sum(vcs),\n )\n\n # Select the indices where one of these classes is present\n idxs = y.index[y.isin(classes)]\n x = x.iloc[idxs]\n y = y.iloc[idxs]\n\n # Uniformly sample columns if required\n if len(x.columns) > ncols_max:\n columns_idxs = rng.choice(\n list(range(len(x.columns))), size=ncols_max, replace=False\n )\n sorted_column_idxs = sorted(columns_idxs)\n selected_columns = list(x.columns[sorted_column_idxs])\n x = x[selected_columns]\n else:\n sorted_column_idxs = list(range(len(x.columns)))\n\n if len(x) > nrows_max:\n # Stratify accordingly\n target_name = y.name\n data = pd.concat((x, y), axis=\"columns\")\n _, subset = train_test_split(\n data,\n test_size=nrows_max,\n stratify=data[target_name],\n shuffle=True,\n random_state=seed,\n )\n x = subset.drop(target_name, axis=\"columns\")\n y = subset[target_name]\n\n # We need to convert categorical columns to string for openml\n categorical_mask = [self.categorical_mask[i] for i in sorted_column_idxs]\n columns = list(x.columns)\n\n return Dataset(\n # Technically this is not the same but it's where it was derived from\n dataset=self.dataset,\n x=x,\n y=y,\n categorical_mask=categorical_mask,\n columns=columns,\n )\n```", "format": "arff", "uploader": "Eddie Bergman", "uploader_id": 32840, "visibility": "public", "creator": "\"Eddie Bergman\"", "contributor": null, "date": "2022-11-17 18:23:19", "update_comment": null, "last_update": "2022-11-17 18:23:19", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111260\/dataset", "kaggle_url": null, "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "credit-g_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset credit-g (31) with seed=0 args.nrows=2000 args.ncols=100 args.nclasses=10 args.no_stratify=True Generated with the following source code: ```python def subsample( self, seed: int, nrows_max: int = 2_000, ncols_max: int = 100, nclasses_max: int = 10, stratified: bool = True, ) -> Dataset: rng = np.random.default_rng(seed) x = self.x y = self.y # Uniformly sample classes = y.unique() if len(classes) > nclasses_max: vcs = y.value_counts() selected_classes = rng.choice( cl " ], "weight": 5 }, "qualities": { "NumberOfInstances": 1000, "NumberOfFeatures": 21, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 7, "NumberOfSymbolicFeatures": 14, "PercentageOfBinaryFeatures": 14.285714285714285, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "AutoCorrelation": 0.5695695695695696, "PercentageOfNumericFeatures": 33.33333333333333, "Dimensionality": 0.021, "PercentageOfSymbolicFeatures": 66.66666666666666, "MajorityClassPercentage": 70, "MajorityClassSize": 700, "MinorityClassPercentage": 30, "MinorityClassSize": 300, "NumberOfBinaryFeatures": 3 }, "tags": [], "features": [ { "name": "class", "index": "20", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "good", "bad" ], [ [ "700", "0" ], [ "0", "300" ] ] ] }, { "name": "checking_status", "index": "0", "type": "nominal", "distinct": "4", "missing": "0", "distr": [ [ "<0", "0<=X<200", ">=200", "no checking" ], [ [ "139", "135" ], [ "164", "105" ], [ "49", "14" ], [ "348", "46" ] ] ] }, { "name": "duration", "index": "1", "type": "numeric", "distinct": "33", "missing": "0", "min": "4", "max": "72", "mean": "21", "stdev": "12" }, { "name": "credit_history", "index": "2", "type": "nominal", "distinct": "5", "missing": "0", "distr": [ [ "no credits\/all paid", "all paid", "existing paid", "delayed previously", "critical\/other existing credit" ], [ [ "15", "25" ], [ "21", "28" ], [ "361", "169" ], [ "60", "28" ], [ "243", "50" ] ] ] }, { "name": "purpose", "index": "3", "type": "nominal", "distinct": "10", "missing": "0", "distr": [ [ "new car", "used car", "furniture\/equipment", "radio\/tv", "domestic appliance", "repairs", "education", "vacation", "retraining", "business", "other" ], [ [ "145", "89" ], [ "86", "17" ], [ "123", "58" ], [ "218", "62" ], [ "8", "4" ], [ "14", "8" ], [ "28", "22" ], [ "0", "0" ], [ "8", "1" ], [ "63", "34" ], [ "7", "5" ] ] ] }, { "name": "credit_amount", "index": "4", "type": "numeric", "distinct": "921", "missing": "0", "min": "250", "max": "18424", "mean": "3271", "stdev": "2823" }, { "name": "savings_status", "index": "5", "type": "nominal", "distinct": "5", "missing": "0", "distr": [ [ "<100", "100<=X<500", "500<=X<1000", ">=1000", "no known savings" ], [ [ "386", "217" ], [ "69", "34" ], [ "52", "11" ], [ "42", "6" ], [ "151", "32" ] ] ] }, { "name": "employment", "index": "6", "type": "nominal", "distinct": "5", "missing": "0", "distr": [ [ "unemployed", "<1", "1<=X<4", "4<=X<7", ">=7" ], [ [ "39", "23" ], [ "102", "70" ], [ "235", "104" ], [ "135", "39" ], [ "189", "64" ] ] ] }, { "name": "installment_commitment", "index": "7", "type": "numeric", "distinct": "4", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "personal_status", "index": "8", "type": "nominal", "distinct": "4", "missing": "0", "distr": [ [ "male div\/sep", "female div\/dep\/mar", "male single", "male mar\/wid", "female single" ], [ [ "30", "20" ], [ "201", "109" ], [ "402", "146" ], [ "67", "25" ], [ "0", "0" ] ] ] }, { "name": "other_parties", "index": "9", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "none", "co applicant", "guarantor" ], [ [ "635", "272" ], [ "23", "18" ], [ "42", "10" ] ] ] }, { "name": "residence_since", "index": "10", "type": "numeric", "distinct": "4", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "property_magnitude", "index": "11", "type": "nominal", "distinct": "4", "missing": "0", "distr": [ [ "real estate", "life insurance", "car", "no known property" ], [ [ "222", "60" ], [ "161", "71" ], [ "230", "102" ], [ "87", "67" ] ] ] }, { "name": "age", "index": "12", "type": "numeric", "distinct": "53", "missing": "0", "min": "19", "max": "75", "mean": "36", "stdev": "11" }, { "name": "other_payment_plans", "index": "13", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "bank", "stores", "none" ], [ [ "82", "57" ], [ "28", "19" ], [ "590", "224" ] ] ] }, { "name": "housing", "index": "14", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "rent", "own", "for free" ], [ [ "109", "70" ], [ "527", "186" ], [ "64", "44" ] ] ] }, { "name": "existing_credits", "index": "15", "type": "numeric", "distinct": "4", "missing": "0", "min": "1", "max": "4", "mean": "1", "stdev": "1" }, { "name": "job", "index": "16", "type": "nominal", "distinct": "4", "missing": "0", "distr": [ [ "unemp\/unskilled non res", "unskilled resident", "skilled", "high qualif\/self emp\/mgmt" ], [ [ "15", "7" ], [ "144", "56" ], [ "444", "186" ], [ "97", "51" ] ] ] }, { "name": "num_dependents", "index": "17", "type": "numeric", "distinct": "2", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "own_telephone", "index": "18", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "none", "yes" ], [ [ "409", "187" ], [ "291", "113" ] ] ] }, { "name": "foreign_worker", "index": "19", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "yes", "no" ], [ [ "667", "296" ], [ "33", "4" ] ] ] } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 0, "total_downloads": 0, "reach": 0, "reuse": 0, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 0 }